© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25730
    Prev
    Next
    INDEX
    Explanations

    articles and possessives before names

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric tokens (including integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这人
    -1.21
    ousness
    -1.16
     it
    -1.13
    osity
    -1.13
    ologists
    -1.09
    踮
    -1.09
    ribune
    -1.04
    érrez
    -1.03
    time
    -1.02
    icide
    -1.01
    POSITIVE LOGITS
    $};
    1.15
    itieren
    1.13
     still
    1.10
     partiellement
    1.09
    Reklama
    1.03
    ：……
    0.99
    taler
    0.98
    esos
    0.98
    FUENTES
    0.97
     теперь
    0.96
    Activations Density 0.066%

    No Known Activations